diff --git a/mlir/test/Dialect/Linalg/vectorize-convolution.mlir b/mlir/test/Dialect/Linalg/vectorize-convolution.mlir
--- a/mlir/test/Dialect/Linalg/vectorize-convolution.mlir
+++ b/mlir/test/Dialect/Linalg/vectorize-convolution.mlir
@@ -583,11 +583,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_sum_memref_1_2_1_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x4x3xf32>, %[[Varg1:.+]]: memref<1xf32>, %[[Varg2:.+]]: memref<4x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x4x3xf32>, %[[FILTER:.+]]: memref<1xf32>, %[[OUTPUT:.+]]: memref<4x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 3, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V1]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x2x3xf32> to vector<4x1x3xf32>
@@ -596,7 +596,7 @@
 // CHECK: %[[V7:.+]] = arith.addf %[[V3]], %[[V5]] : vector<4x1x3xf32>
 // CHECK: %[[V8:.+]] = vector.insert_strided_slice %[[V6]], %[[V1]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V9:.+]] = vector.insert_strided_slice %[[V7]], %[[V8]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
-// CHECK: vector.transfer_write %[[V9]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
+// CHECK: vector.transfer_write %[[V9]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
 
 // -----
 
@@ -609,11 +609,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_max_memref_1_2_1_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x4x3xf32>, %[[Varg1:.+]]: memref<1xf32>, %[[Varg2:.+]]: memref<4x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x4x3xf32>, %[[FILTER:.+]]: memref<1xf32>, %[[OUTPUT:.+]]: memref<4x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 3, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V1]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x2x3xf32> to vector<4x1x3xf32>
@@ -622,7 +622,7 @@
 // CHECK: %[[V7:.+]] = arith.maxf %[[V3]], %[[V5]] : vector<4x1x3xf32>
 // CHECK: %[[V8:.+]] = vector.insert_strided_slice %[[V6]], %[[V1]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V9:.+]] = vector.insert_strided_slice %[[V7]], %[[V8]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
-// CHECK: vector.transfer_write %[[V9]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
+// CHECK: vector.transfer_write %[[V9]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
 
 // -----
 
@@ -637,12 +637,12 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_sum_i8i8i32_memref_1_2_1_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x4x3xi8>, %[[Varg1:.+]]: memref<1xi8>, %[[Varg2:.+]]: memref<4x2x3xi32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x4x3xi8>, %[[FILTER:.+]]: memref<1xi8>, %[[OUTPUT:.+]]: memref<4x2x3xi32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vc0_i8:.+]] = arith.constant 0 : i8
 // CHECK-DAG: %[[Vc0_i32:.+]] = arith.constant 0 : i32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i8]] {in_bounds = [true, true, true]} : memref<4x4x3xi8>, vector<4x4x3xi8>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i32]] {in_bounds = [true, true, true]} : memref<4x2x3xi32>, vector<4x2x3xi32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i8]] {in_bounds = [true, true, true]} : memref<4x4x3xi8>, vector<4x4x3xi8>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i32]] {in_bounds = [true, true, true]} : memref<4x2x3xi32>, vector<4x2x3xi32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xi8> to vector<4x1x3xi8>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 3, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xi8> to vector<4x1x3xi8>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V1]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x2x3xi32> to vector<4x1x3xi32>
@@ -653,7 +653,7 @@
 // CHECK: %[[V9:.+]] = arith.addi %[[V8]], %[[V5]] : vector<4x1x3xi32>
 // CHECK: %[[V10:.+]] = vector.insert_strided_slice %[[V7]], %[[V1]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xi32> into vector<4x2x3xi32>
 // CHECK: %[[V11:.+]] = vector.insert_strided_slice %[[V9]], %[[V10]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xi32> into vector<4x2x3xi32>
-// CHECK: vector.transfer_write %[[V11]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xi32>, memref<4x2x3xi32>
+// CHECK: vector.transfer_write %[[V11]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xi32>, memref<4x2x3xi32>
 // CHECK: return
 
 // -----
@@ -669,12 +669,12 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_max_i8i8i32_memref_1_2_1_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x4x3xi8>, %[[Varg1:.+]]: memref<1xi8>, %[[Varg2:.+]]: memref<4x2x3xi32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x4x3xi8>, %[[FILTER:.+]]: memref<1xi8>, %[[OUTPUT:.+]]: memref<4x2x3xi32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vc0_i8:.+]] = arith.constant 0 : i8
 // CHECK-DAG: %[[Vc0_i32:.+]] = arith.constant 0 : i32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i8]] {in_bounds = [true, true, true]} : memref<4x4x3xi8>, vector<4x4x3xi8>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i32]] {in_bounds = [true, true, true]} : memref<4x2x3xi32>, vector<4x2x3xi32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i8]] {in_bounds = [true, true, true]} : memref<4x4x3xi8>, vector<4x4x3xi8>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vc0_i32]] {in_bounds = [true, true, true]} : memref<4x2x3xi32>, vector<4x2x3xi32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xi8> to vector<4x1x3xi8>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 3, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xi8> to vector<4x1x3xi8>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V1]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x2x3xi32> to vector<4x1x3xi32>
@@ -685,7 +685,7 @@
 // CHECK: %[[V9:.+]] = arith.maxsi %[[V8]], %[[V5]] : vector<4x1x3xi32>
 // CHECK: %[[V10:.+]] = vector.insert_strided_slice %[[V7]], %[[V1]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xi32> into vector<4x2x3xi32>
 // CHECK: %[[V11:.+]] = vector.insert_strided_slice %[[V9]], %[[V10]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xi32> into vector<4x2x3xi32>
-// CHECK: vector.transfer_write %[[V11]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xi32>, memref<4x2x3xi32>
+// CHECK: vector.transfer_write %[[V11]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xi32>, memref<4x2x3xi32>
 // CHECK: return
 
 // -----
@@ -699,11 +699,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_sum_memref_2_2_2_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x6x3xf32>, %[[Varg1:.+]]: memref<2xf32>, %[[Varg2:.+]]: memref<4x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x6x3xf32>, %[[FILTER:.+]]: memref<2xf32>, %[[OUTPUT:.+]]: memref<4x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x6x3xf32>, vector<4x6x3xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x6x3xf32>, vector<4x6x3xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x6x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 3, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x6x3xf32> to vector<4x1x3xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 2, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x6x3xf32> to vector<4x1x3xf32>
@@ -716,7 +716,7 @@
 // CHECK: %[[V11:.+]] = arith.addf %[[V5]], %[[V9]] : vector<4x1x3xf32>
 // CHECK: %[[V12:.+]] = vector.insert_strided_slice %[[V10]], %[[V1]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V13:.+]] = vector.insert_strided_slice %[[V11]], %[[V12]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
-// CHECK: vector.transfer_write %[[V13:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
+// CHECK: vector.transfer_write %[[V13:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
 
 
 // -----
@@ -730,11 +730,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_ncw_sum_memref_1_2_1_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x3x4xf32>, %[[Varg1:.+]]: memref<1xf32>, %[[Varg2:.+]]: memref<4x3x2xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x3x4xf32>, %[[FILTER:.+]]: memref<1xf32>, %[[OUTPUT:.+]]: memref<4x3x2xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x4xf32>, vector<4x3x4xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x2xf32>, vector<4x3x2xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x4xf32>, vector<4x3x4xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x2xf32>, vector<4x3x2xf32>
 // CHECK: %[[V2:.+]] = vector.transpose %[[V0]], [0, 2, 1] : vector<4x3x4xf32> to vector<4x4x3xf32>
 // CHECK: %[[V3:.+]] = vector.transpose %[[V1]], [0, 2, 1] : vector<4x3x2xf32> to vector<4x2x3xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V2]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x1x3xf32>
@@ -746,7 +746,7 @@
 // CHECK: %[[V10:.+]] = vector.insert_strided_slice %[[V8]], %[[V3]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V11:.+]] = vector.insert_strided_slice %[[V9]], %[[V10]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V12:.+]] = vector.transpose %[[V11]], [0, 2, 1] : vector<4x2x3xf32> to vector<4x3x2xf32>
-// CHECK: vector.transfer_write %[[V12:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x3x2xf32>, memref<4x3x2xf32>
+// CHECK: vector.transfer_write %[[V12:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x3x2xf32>, memref<4x3x2xf32>
 
 
 // -----
@@ -760,15 +760,15 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_sum_mixed_type_memref_1_2_1_1
-// CHECK-SAME: (%[[Varg0:.+]]: memref<1x2x3xf16>, %[[Varg1:.+]]: memref<1xf16>, %[[Varg2:.+]]: memref<1x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<1x2x3xf16>, %[[FILTER:.+]]: memref<1xf16>, %[[OUTPUT:.+]]: memref<1x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f16
 // CHECK-DAG: %[[Vcst_0:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<1x2x3xf16>, vector<1x2x3xf16>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst_0]] {in_bounds = [true, true, true]} : memref<1x2x3xf32>, vector<1x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<1x2x3xf16>, vector<1x2x3xf16>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst_0]] {in_bounds = [true, true, true]} : memref<1x2x3xf32>, vector<1x2x3xf32>
 // CHECK: %[[V2:.+]] = arith.extf %[[V0]] : vector<1x2x3xf16> to vector<1x2x3xf32>
 // CHECK: %[[V3:.+]] = arith.addf %[[V2]], %[[V1]] : vector<1x2x3xf32>
-// CHECK: vector.transfer_write %[[V3:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<1x2x3xf32>, memref<1x2x3xf32>
+// CHECK: vector.transfer_write %[[V3:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<1x2x3xf32>, memref<1x2x3xf32>
 
 // -----
 
@@ -781,16 +781,16 @@
 }
 
 // CHECK-LABEL: func.func @pooling_nwc_sum_memref_2_2_2_1
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x4x3xf32>, %[[Varg1:.+]]: memref<2xf32>, %[[Varg2:.+]]: memref<4x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x4x3xf32>, %[[FILTER:.+]]: memref<2xf32>, %[[OUTPUT:.+]]: memref<4x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x4x3xf32>, vector<4x4x3xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
 // CHECK: %[[V2:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 0, 0], sizes = [4, 2, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x2x3xf32>
 // CHECK: %[[V3:.+]] = vector.extract_strided_slice %[[V0]] {offsets = [0, 2, 0], sizes = [4, 2, 3], strides = [1, 1, 1]} : vector<4x4x3xf32> to vector<4x2x3xf32>
 // CHECK: %[[V4:.+]] = arith.addf %[[V2]], %[[V1]] : vector<4x2x3xf32>
 // CHECK: %[[V5:.+]] = arith.addf %[[V3]], %[[V4]] : vector<4x2x3xf32>
-// CHECK: vector.transfer_write %[[V5:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
+// CHECK: vector.transfer_write %[[V5:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
 
 
 // -----
@@ -804,11 +804,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_ncw_sum_memref_2_2_2_3
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x3x6xf32>, %[[Varg1:.+]]: memref<2xf32>, %[[Varg2:.+]]: memref<4x3x2xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x3x6xf32>, %[[FILTER:.+]]: memref<2xf32>, %[[OUTPUT:.+]]: memref<4x3x2xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x6xf32>, vector<4x3x6xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x2xf32>, vector<4x3x2xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x6xf32>, vector<4x3x6xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x3x2xf32>, vector<4x3x2xf32>
 // CHECK: %[[V2:.+]] = vector.transpose %[[V0]], [0, 2, 1] : vector<4x3x6xf32> to vector<4x6x3xf32>
 // CHECK: %[[V3:.+]] = vector.transpose %[[V1]], [0, 2, 1] : vector<4x3x2xf32> to vector<4x2x3xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V2]] {offsets = [0, 0, 0], sizes = [4, 1, 3], strides = [1, 1, 1]} : vector<4x6x3xf32> to vector<4x1x3xf32>
@@ -824,7 +824,7 @@
 // CHECK: %[[V14:.+]] = vector.insert_strided_slice %[[V12]], %[[V3]] {offsets = [0, 0, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V15:.+]] = vector.insert_strided_slice %[[V13]], %[[V14]] {offsets = [0, 1, 0], strides = [1, 1, 1]} : vector<4x1x3xf32> into vector<4x2x3xf32>
 // CHECK: %[[V16:.+]] = vector.transpose %[[V15]], [0, 2, 1] : vector<4x2x3xf32> to vector<4x3x2xf32>
-// CHECK: vector.transfer_write %[[V16:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x3x2xf32>, memref<4x3x2xf32>
+// CHECK: vector.transfer_write %[[V16:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x3x2xf32>, memref<4x3x2xf32>
 
 // -----
 
@@ -837,11 +837,11 @@
 }
 
 // CHECK-LABEL: func.func @pooling_ncw_sum_memref_2_3_2_1
-// CHECK-SAME: (%[[Varg0:.+]]: memref<4x2x5xf32>, %[[Varg1:.+]]: memref<2xf32>, %[[Varg2:.+]]: memref<4x2x3xf32>)
+// CHECK-SAME: (%[[INPUT:.+]]: memref<4x2x5xf32>, %[[FILTER:.+]]: memref<2xf32>, %[[OUTPUT:.+]]: memref<4x2x3xf32>)
 // CHECK-DAG: %[[Vc0:.+]] = arith.constant 0 : index
 // CHECK-DAG: %[[Vcst:.+]] = arith.constant 0.000000e+00 : f32
-// CHECK: %[[V0:.+]] = vector.transfer_read %[[Varg0]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x5xf32>, vector<4x2x5xf32>
-// CHECK: %[[V1:.+]] = vector.transfer_read %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
+// CHECK: %[[V0:.+]] = vector.transfer_read %[[INPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x5xf32>, vector<4x2x5xf32>
+// CHECK: %[[V1:.+]] = vector.transfer_read %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]], %[[Vcst]] {in_bounds = [true, true, true]} : memref<4x2x3xf32>, vector<4x2x3xf32>
 // CHECK: %[[V2:.+]] = vector.transpose %[[V0]], [0, 2, 1] : vector<4x2x5xf32> to vector<4x5x2xf32>
 // CHECK: %[[V3:.+]] = vector.transpose %[[V1]], [0, 2, 1] : vector<4x2x3xf32> to vector<4x3x2xf32>
 // CHECK: %[[V4:.+]] = vector.extract_strided_slice %[[V2]] {offsets = [0, 0, 0], sizes = [4, 3, 2], strides = [1, 1, 1]} : vector<4x5x2xf32> to vector<4x3x2xf32>
@@ -849,4 +849,4 @@
 // CHECK: %[[V6:.+]] = arith.addf %[[V4]], %[[V3]] : vector<4x3x2xf32>
 // CHECK: %[[V7:.+]] = arith.addf %[[V5]], %[[V6]] : vector<4x3x2xf32>
 // CHECK: %[[V8:.+]] = vector.transpose %[[V7]], [0, 2, 1] : vector<4x3x2xf32> to vector<4x2x3xf32>
-// CHECK: vector.transfer_write %[[V8:.+]], %[[Varg2]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>
+// CHECK: vector.transfer_write %[[V8:.+]], %[[OUTPUT]][%[[Vc0]], %[[Vc0]], %[[Vc0]]] {in_bounds = [true, true, true]} : vector<4x2x3xf32>, memref<4x2x3xf32>